
# import the required library
import warnings
import numpy as np
import pandas as pd
import statsmodels.api as sm
import datetime
import matplotlib.pyplot as plt
import seaborn as sns
import folium
from mpl_toolkits.mplot3d import Axes3D


# as we are analysing data based on single file add as an constant
FILE_PATH = 'assets/strava.csv'

#supress any pandas warning for inplace update
warnings.filterwarnings("ignore")

def load_and_pre_process_data(file_path):
    
    # load the data in pandas dataframe
    df = pd.read_csv(file_path)

    # create the buckets to find the differnt exercise
    buckets = [ i for i in range(100 , 2, -1 )]

    # column name required for analysis
    columns = ['timestamp', 'distance', 'speed', 'heart_rate', 'Power', 'position_lat' , 'position_long', 'enhanced_altitude', 'cadence']

    # filter the required columns 
    res  = df[columns]

    # parse the colums are required datatype
    res['timestamp'] = pd.to_datetime(res['timestamp'])
    res['date'] = res['timestamp'].dt.date
    res['date'] = pd.to_datetime(res['date'])

    # substract the next/prev value form current to find the start/end time of exercise
    res['next'] = res['distance'].diff(periods=-1)
    res['prev'] = res['distance'].diff()

    # assign a bucket to each exercise
    res['bucket'] = res['prev'].apply(lambda x : buckets.pop()  if x < 0 else np.nan)

    # assign 1 to first bucket
    res['bucket'].iloc[0] = 1

    #forward will the bucker number to identify a exercise duration 
    res['bucket'] = res['bucket'].ffill()

    return res


### group the data to find the activity type and other analyis 

def process_and_agg_data(raw_data):

    # get the group for different bucket
    groups  = raw_data.groupby(['bucket'] , as_index=False)

    # Distance traveled during each activity and scale up to KM.
    data = groups[['distance']].agg(lambda x :  0.001*(x.iloc[-1] - x.iloc[0]))

    ## Activity duration and convert it to hour
    data['duration'] = groups[['timestamp']].agg(lambda x :  (x.iloc[-1] - x.iloc[0]).total_seconds()/3600)['timestamp']

    ## calculate average speed for the activity that wwe will use find activity.
    data['avg_speed'] = data['distance'] / data['duration']

    # start time of activity
    data['start_time'] = groups[['timestamp']].first()['timestamp']

    #minimum heart rate during activity 
    data['min_hr'] = groups[['heart_rate']].min()['heart_rate']

    #maximum heart rate during activity
    data['max_hr'] = groups[['heart_rate']].max()['heart_rate']

    return data


# update the data with activity type
def data_updated_activity(file_path):

    raw_data = load_and_pre_process_data(file_path)
    
    data = process_and_agg_data(raw_data)

    # bicycle activity
    bicycle_buckets = data[data['avg_speed']>12]['bucket'].to_numpy()

    # update activity based on assumption that average running speed is not more then 12 KM/Hour
    raw_data['activity_type'] = raw_data['bucket'].apply(lambda x : 'Bicycle' if x in bicycle_buckets else 'Running' )

    return raw_data


# Load data for violin plot
data = load_and_pre_process_data(FILE_PATH)

fig = plt.subplots(figsize = (9,7))
sns.violinplot(data=data , y='heart_rate').set(title = 'Distribution of Heart Rate' , ylabel = 'Heart Rate' )
plt.legend(['Min  - ' + str(data['heart_rate'].min()),
            'Max - ' + str(data['heart_rate'].max()),
            'Mean - ' + str(int(data['heart_rate'].mean()))]
           , fontsize = 'x-large')
plt.show()


# load the data again to avoid any data collision if cells are not run in order
power_heart_rate  = load_and_pre_process_data(FILE_PATH)[['heart_rate', 'Power']].dropna().reset_index()

#add a new scatter plot 
fig = plt.subplots(figsize = (10,5))
sns.scatterplot(data = power_heart_rate , x = 'Power' , y = 'heart_rate').set(title = 'Scatterplot of heart rate vs power' , ylabel = 'Heart rate')

#regression analysis to draw a line
X = sm.add_constant(power_heart_rate['Power'])
model = sm.OLS(power_heart_rate['heart_rate'] , X).fit()

predict = model.predict(X)

plt.plot(power_heart_rate['Power'] ,predict , color = 'purple' , label = 'Regression line ')
plt.legend(loc="upper left")
plt.show()


# get agg data 
running  = process_and_agg_data(load_and_pre_process_data(FILE_PATH))

### Analysis assumes speed less then 12KM/Hour as running.
running = running[running['avg_speed']<12]


fig = plt.subplots(figsize = (12,8))

#use custom ticks window of 5  
y_ticks = [5 * i for  i in  range(40)]

x_ticks = running['start_time'].dt.date.apply(lambda x : str(x))

#plot min heart rate overtime for activity
sns.lineplot(x = 'start_time' ,  y = 'min_hr' ,  data = running,
             linewidth = 2.5, marker = 'o' , markersize = 10).set(
    title = 'Heart rate over time' , xlabel = 'Exercise date', ylabel = 'Heart rate' ,  yticks = y_ticks , xticks = x_ticks)

#plot max heart rate overtime for activity
sns.lineplot(x = 'start_time' ,  y = 'max_hr' ,  data = running,
             linewidth = 2.5, marker = 'o' , markersize = 10).set(
    title = 'Heart rate over time' , xlabel = 'Exercise date', ylabel = 'Heart rate' ,  yticks = y_ticks, xticks = x_ticks)

# average heart rate for healthy person is between 90-153 for age group 40-45

# Plot line for lower heart rate limit for age round
sns.lineplot(x = 'start_time' ,  y = 90 ,  data = running,
             linewidth = 2.5 , label = 'Lower heart rate for age group 40-45')

## Plot line for upper heart rate limit for age round
sns.lineplot(x = 'start_time' ,  y = 153 ,  data = running,
             linewidth = 2.5 , label = 'Upper heart rate for age group 40-45')

# rotate the ticks for clearn x axis
plt.xticks(rotation=85)
line = plt.gca().lines
plt.fill_between(line[0].get_xdata(),line[0].get_ydata(), line[1].get_ydata(), color='grey', alpha=.5)
plt.legend(loc="upper left")
plt.show()


#load data and update activity type
data = data_updated_activity(FILE_PATH)

fig = plt.subplots(figsize = (15,8))
g = sns.lineplot(x = 'distance' ,  y = 'heart_rate' , data = data, hue = 'activity_type', style = 'activity_type',
             linewidth = 2.5, marker = 'o' , markersize = 10).set(
    title = 'Line plot - distance and heart rate for different activity' , xlabel = 'distance covered in meter', ylabel = 'Heart rate')
plt.show()


def plot_3d(data):

    # add a new figure with size 6 6
    fig = plt.figure(figsize = (6,6))
    ax = fig.add_subplot(projection='3d')
    
    #add a 3d scatter plot 
    artists=ax.scatter(data["Power"], data["heart_rate"], data["cadence"],
                   s=5, c=data["cadence"], cmap='Blues')

    #add lable to colorbar
    plt.colorbar(artists).set_label("Power (watts)")

    # add lable to access
    ax.set_xlabel('Longitude')
    ax.set_ylabel('Latitude')
    ax.set_zlabel('cadence')
    plt.show()

data = data_updated_activity(FILE_PATH)[['heart_rate' , 'Power' , 'bucket' , 'cadence']].dropna()
for bucket in data['bucket'].unique():
    bucket_data = data[data['bucket'] == bucket]
    plot_3d(bucket_data)


# prepare map attribute 
def prepare_gis_map(data , title):


    #prepare the data to map
    data  = data * (180 / 2**31 )

    start = [data["position_lat"].iloc[0], data["position_long"].iloc[0]]
    end   = [data["position_lat"].iloc[-1], data["position_long"].iloc[-1]]
    
    # start lat/long
    m = folium.Map(location= start , zoom_start=14)
    
    #add title to map
    title_html = f'<h3 align="center" style="font-size:22px;color:blue; font-family:Brush Script MT,cursive"><b>{title} </b></h3>'
    m.get_root().html.add_child(folium.Element(title_html))
    
    # add a start marker
    folium.Marker(start, popup="Start" , icon=folium.Icon("green") ).add_to(m)

    # add a end marker
    folium.Marker(end,   popup="Stop" , icon=folium.Icon("green")).add_to(m)
    
    route = folium.PolyLine(locations=zip(data["position_lat"], data["position_long"]),
                    weight=5, color='blue').add_to(m)
   
    return m 

data = data_updated_activity(FILE_PATH)[['position_lat' , 'position_long' , 'bucket' , 'activity_type' , 'timestamp']].dropna()
for bucket in data['bucket'].unique():
    bucket_data = data[data['bucket'] == bucket]
    title = f'''Activity start time - {bucket_data['timestamp'].iloc[0]} 
              Activity Type - {bucket_data['activity_type'].iloc[0]}'''
    display(prepare_gis_map(bucket_data[['position_lat' , 'position_long' ]] , title))


print

Exploring Exercise and Heart Rate Dynamics: A Comprehensive Analysis¶

Assumption¶

Reference¶

`Figure 1` - Visualizing Data Distribution for Heart Rate¶

Analysis of Violin Plot -¶

`Figure 2` - Correlation Between Power and Heart Rate¶

Analysis scattor plot-¶

`Figure 3` - Effects of Exercise on Heart Rate¶

`Result`¶

`Figure 5` Heart Rate and Distance¶

Visual observation for differnt activity type¶

`Figure 6` - Heart Rate , Power and cadence relationship¶

Result - 3d plot¶

`Figure 7` `Geographical Information Systems`¶

Conclusions and Recommendations¶

Exploring Exercise and Heart Rate Dynamics: A Comprehensive Analysis¶

Assumption¶

Reference¶

Figure 1 - Visualizing Data Distribution for Heart Rate¶

Analysis of Violin Plot -¶

Figure 2 - Correlation Between Power and Heart Rate¶

Analysis scattor plot-¶

Figure 3 - Effects of Exercise on Heart Rate¶

Result¶

Figure 5 Heart Rate and Distance¶

Visual observation for differnt activity type¶

Figure 6 - Heart Rate , Power and cadence relationship¶

Result - 3d plot¶

Figure 7 Geographical Information Systems¶

Conclusions and Recommendations¶

`Figure 1` - Visualizing Data Distribution for Heart Rate¶

`Figure 2` - Correlation Between Power and Heart Rate¶

`Figure 3` - Effects of Exercise on Heart Rate¶

`Result`¶

`Figure 5` Heart Rate and Distance¶

`Figure 6` - Heart Rate , Power and cadence relationship¶

`Figure 7` `Geographical Information Systems`¶